Skip to content
Projects

rtqichen/ffjord has 671 GitHub stars and 140 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-15 22:24 UTC. Last push 2020-09-22.

How these counts are measured

Measured star growth

in 24h
0
in 7 days
Collecting history
in 15 days
Collecting history
in 1 month
Collecting history

Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.

About

code for "FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models".

Developer Tools

README.md

Original

Free-form Jacobian of Reversible Dynamics (FFJORD)

Code for reproducing the experiments in the paper:

Will Grathwohl*, Ricky T. Q. Chen*, Jesse Bettencourt, Ilya Sutskever, David Duvenaud. "FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models." International Conference on Learning Representations (2019). [arxiv] [bibtex]

Prerequisites

Install torchdiffeq from https://github.com/rtqichen/torchdiffeq.

Usage

Different scripts are provided for different datasets. To see all options, use the -h flag.

Toy 2d:

python train_toy.py --data 8gaussians --dims 64-64-64 --layer_type concatsquash --save experiment1

Tabular datasets from MAF:

python train_tabular.py --data miniboone --nhidden 2 --hdim_factor 20 --num_blocks 1 --nonlinearity softplus --batch_size 1000 --lr 1e-3

MNIST/CIFAR10:

python train_cnf.py --data mnist --dims 64,64,64 --strides 1,1,1,1 --num_blocks 2 --layer_type concat --multiscale True --rademacher True

VAE Experiments (based on Sylvester VAE):

python train_vae_flow.py --dataset mnist --flow cnf_rank --rank 64 --dims 1024-1024 --num_blocks 2

Glow / Real NVP experiments are run using train_discrete_toy.py and train_discrete_tabular.py.

Datasets

Tabular (UCI + BSDS300)

Follow instructions from https://github.com/gpapamak/maf and place them in data/.

VAE datasets

Follow instructions from https://github.com/riannevdberg/sylvester-flows and place them in data/.

Bespoke Flows

Here's a fun script that you can use to create your own 2D flow from an image!

python train_img2d.py --img imgs/github.png --save github_flow